• Playground
  • Models
  • Rankings
  • Support
All systems operational
© 2026 BoundlessTermssupport@boundless.network
All models

DeepSeek V4.1 Flash 1017 Abliterated

by DeepSeek

DeepSeek V4.1 Flash 1017 Abliterated is DeepSeek V4.1 Flash 1017 with its refusal behaviour removed by abliteration, designed to answer requests the original model declines. It keeps the base model's coding, reasoning, and tool use, with a 1,048,576-token context window.


Best for: Uncensored coding and reasoning with a long context.
1M context
  • Text
  • Reasoning
  • Tool use
  • Abliterated
boundless/deepseek-v4.1-flash-1017-abliteratedApply for access

Pricing

Pricing
USD per 1M tokens. Cheapest input plus output first.
ProviderInputCached inputOutput
BoundlessBest price$0.24$0.012$0.96
Baseten$0.30$0.007$1.20
DigitalOcean$0.30$0.006$1.20
Fireworks$0.30$0.006$1.20
Together AI$0.30$0.006$1.20
Venice$0.33$0.00825$1.32
What one request costs
Prompt94Ktokens
Cached prefix66Ktokens
Reply2Ktokens

$0.0090

per request to DeepSeek V4.1 Flash 1017 Abliterated

Prompt
75.2%
Cached
8.8%
Reply
16%

DeepSeek V4.1 Flash 1017 Abliterated: $0.0089976 per request

94,000 prompt tokens, 65,800 of them cached, and 1,500 reply tokens.

The same request, across other models